{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T19:25:45Z","timestamp":1781292345547,"version":"3.54.1"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2024,12,10]],"date-time":"2024-12-10T00:00:00Z","timestamp":1733788800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,10]],"date-time":"2024-12-10T00:00:00Z","timestamp":1733788800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1007\/s10489-024-05986-x","type":"journal-article","created":{"date-parts":[[2024,12,10]],"date-time":"2024-12-10T08:55:33Z","timestamp":1733820933000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["SANet: similarity aggregation and semantic fusion for few-shot semantic segmentation"],"prefix":"10.1007","volume":"55","author":[{"given":"Minrui","family":"Ye","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,12,10]]},"reference":[{"key":"5986_CR1","doi-asserted-by":"crossref","unstructured":"Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 3431\u20133440","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"5986_CR2","unstructured":"Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: Towards real-time object detection with region proposal networks. Adv Neural Inf Process Syst 28"},{"key":"5986_CR3","doi-asserted-by":"crossref","unstructured":"Ronneberger O, Fischer P, Brox T (2015) U-net: Convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-assisted intervention\u2013MICCAI 2015: 18th International Conference, Munich, Germany, 5-9 October, 2015, Proceedings, Part III 18, pp 234\u2013241 . Springer","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"5986_CR4","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"5986_CR5","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: Unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 779\u2013788","DOI":"10.1109\/CVPR.2016.91"},{"key":"5986_CR6","doi-asserted-by":"crossref","unstructured":"He K, Gkioxari G, Doll\u00e1r P, Girshick R (2017) Mask r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, pp 2961\u20132969","DOI":"10.1109\/ICCV.2017.322"},{"key":"5986_CR7","doi-asserted-by":"crossref","unstructured":"Huang G, Liu Z, Van Der\u00a0Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 4700\u20134708","DOI":"10.1109\/CVPR.2017.243"},{"key":"5986_CR8","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Doll\u00e1r P, Girshick R, He K, Hariharan B, Belongie S (2017) Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 2117\u20132125","DOI":"10.1109\/CVPR.2017.106"},{"key":"5986_CR9","doi-asserted-by":"crossref","unstructured":"Shaban A, Bansal S, Liu Z, Essa I, Boots B (2017) One-shot learning for semantic segmentation. arXiv:1709.03410","DOI":"10.5244\/C.31.167"},{"key":"5986_CR10","unstructured":"Snell J, Swersky K, Zemel R (2017) Prototypical networks for few-shot learning. Adv Neural Inf Process Syst 30"},{"key":"5986_CR11","unstructured":"Dong N, Xing EP (2018) Few-shot semantic segmentation with prototype learning. In: BMVC, vol 3, p 4"},{"key":"5986_CR12","doi-asserted-by":"crossref","unstructured":"Lu Z, He S, Zhu X, Zhang L, Song Y-Z, Xiang T (2021) Simpler is better: Few-shot semantic segmentation with classifier weight transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 8741\u20138750","DOI":"10.1109\/ICCV48922.2021.00862"},{"key":"5986_CR13","doi-asserted-by":"crossref","unstructured":"Wang K, Liew JH, Zou Y, Zhou D, Feng J (2019) Panet: Few-shot image semantic segmentation with prototype alignment. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 9197\u20139206","DOI":"10.1109\/ICCV.2019.00929"},{"issue":"9","key":"5986_CR14","doi-asserted-by":"publisher","first-page":"3855","DOI":"10.1109\/TCYB.2020.2992433","volume":"50","author":"X Zhang","year":"2020","unstructured":"Zhang X, Wei Y, Yang Y, Huang TS (2020) Sg-one: Similarity guidance network for one-shot semantic segmentation. IEEE Trans Cybern 50(9):3855\u20133865","journal-title":"IEEE Trans Cybern"},{"issue":"2","key":"5986_CR15","doi-asserted-by":"publisher","first-page":"1050","DOI":"10.1109\/TPAMI.2020.3013717","volume":"44","author":"Z Tian","year":"2020","unstructured":"Tian Z, Zhao H, Shu M, Yang Z, Li R, Jia J (2020) Prior guided feature enrichment network for few-shot segmentation. IEEE Trans Patt Anal Mach Intell 44(2):1050\u20131065","journal-title":"IEEE Trans Patt Anal Mach Intell"},{"key":"5986_CR16","doi-asserted-by":"crossref","unstructured":"Wang H, Zhang X, Hu Y, Yang Y, Cao X, Zhen X (2020) Few-shot semantic segmentation with democratic attention networks. In: Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, 23\u201328 August, 2020, Proceedings, Part XIII 16, pp 730\u2013746 . Springer","DOI":"10.1007\/978-3-030-58601-0_43"},{"key":"5986_CR17","first-page":"21984","volume":"34","author":"G Zhang","year":"2021","unstructured":"Zhang G, Kang G, Yang Y, Wei Y (2021) Few-shot segmentation via cycle-consistent transformer. Adv Neural Inf Process Syst 34:21984\u201321996","journal-title":"Adv Neural Inf Process Syst"},{"key":"5986_CR18","doi-asserted-by":"crossref","unstructured":"Shi X, Wei D, Zhang Y, Lu D, Ning M, Chen J, Ma K, Zheng Y (2022) Dense cross-query-and-support attention weighted mask aggregation for few-shot segmentation. In: European Conference on Computer Vision, pp 151\u2013168 . Springer","DOI":"10.1007\/978-3-031-20044-1_9"},{"key":"5986_CR19","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I (2017) Attention is all you need. Adv Neural Inf Process Syst 30"},{"key":"5986_CR20","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Doll\u00e1r P, Zitnick CL (2014) Microsoft coco: Common objects in context. In: Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, 6-12 September, 2014, Proceedings, Part V 13, pp 740\u2013755 . Springer","DOI":"10.1007\/978-3-319-10602-1_48"},{"issue":"4","key":"5986_CR21","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"L-C Chen","year":"2017","unstructured":"Chen L-C, Papandreou G, Kokkinos I, Murphy K, Yuille AL (2017) Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Trans Pattern Anal Mach Intell 40(4):834\u2013848","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"5986_CR22","doi-asserted-by":"crossref","unstructured":"Zhao H, Shi J, Qi X, Wang X, Jia J (2017) Pyramid scene parsing network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 2881\u20132890","DOI":"10.1109\/CVPR.2017.660"},{"key":"5986_CR23","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S, et al (2020) An image is worth 16x16 words: Transformers for image recognition at scale. arXiv:2010.11929"},{"key":"5986_CR24","doi-asserted-by":"crossref","unstructured":"Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, Lin S, Guo B (2021) Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 10012\u201310022","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"5986_CR25","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M et al (2015) Imagenet large scale visual recognition challenge. Int J Comput Vis 115:211\u2013252","journal-title":"Int J Comput Vis"},{"key":"5986_CR26","doi-asserted-by":"crossref","unstructured":"Yang Y, Chen Q, Feng Y, Huang T (2023) Mianet: aggregating unbiased instance and general information for few-shot semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 7131\u20137140","DOI":"10.1109\/CVPR52729.2023.00689"},{"key":"5986_CR27","doi-asserted-by":"crossref","unstructured":"Zhang C, Lin G, Liu F, Yao R, Shen C (2019) Canet: Class-agnostic segmentation networks with iterative refinement and attentive few-shot learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 5217\u20135226","DOI":"10.1109\/CVPR.2019.00536"},{"key":"5986_CR28","doi-asserted-by":"crossref","unstructured":"Lang C, Cheng G, Tu B, Han J (2022) Learning what not to segment: A new perspective on few-shot segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 8057\u20138067","DOI":"10.1109\/CVPR52688.2022.00789"},{"key":"5986_CR29","doi-asserted-by":"crossref","unstructured":"Liu W, Zhang C, Lin G, Liu F (2020) Crnet: Cross-reference networks for few-shot segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 4165\u20134173","DOI":"10.1109\/CVPR42600.2020.00422"},{"key":"5986_CR30","doi-asserted-by":"crossref","unstructured":"Min J, Kang D, Cho M (2021) Hypercorrelation squeeze for few-shot segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 6941\u20136952","DOI":"10.1109\/ICCV48922.2021.00686"},{"key":"5986_CR31","doi-asserted-by":"crossref","unstructured":"Sun J, Shen Z, Wang Y, Bao H, Zhou X (2021) Loftr: Detector-free local feature matching with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 8922\u20138931","DOI":"10.1109\/CVPR46437.2021.00881"},{"key":"5986_CR32","unstructured":"Cao L, Guo Y, Yuan Y, Jin Q (2022) Prototype as query for few shot semantic segmentation. arXiv:2211.14764"},{"key":"5986_CR33","doi-asserted-by":"crossref","unstructured":"Wang X, Girshick R, Gupta A, He K (2018) Non-local neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 7794\u20137803","DOI":"10.1109\/CVPR.2018.00813"},{"key":"5986_CR34","doi-asserted-by":"crossref","unstructured":"Fu J, Liu J, Tian H, Li Y, Bao Y, Fang Z, Lu H (2019) Dual attention network for scene segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 3146\u20133154","DOI":"10.1109\/CVPR.2019.00326"},{"key":"5986_CR35","doi-asserted-by":"crossref","unstructured":"Zhuge Y, Shen C (2021) Deep reasoning network for few-shot semantic segmentation. In: Proceedings of the 29th ACM International Conference on Multimedia, pp 5344\u20135352","DOI":"10.1145\/3474085.3475658"},{"issue":"10","key":"5986_CR36","doi-asserted-by":"publisher","first-page":"7853","DOI":"10.1007\/s00521-022-08077-5","volume":"35","author":"J Wang","year":"2023","unstructured":"Wang J, Chen Y, Dong Z, Gao M (2023) Improved yolov5 network for real-time multi-scale traffic sign detection. Neural Comput Appl 35(10):7853\u20137865","journal-title":"Neural Comput Appl"},{"key":"5986_CR37","unstructured":"Iqbal E, Safarov S, Bang S (2022) Msanet: Multi-similarity and attention guidance for boosting few-shot segmentation. arXiv:2206.09667"},{"key":"5986_CR38","doi-asserted-by":"crossref","unstructured":"Yang B, Liu C, Li B, Jiao J, Ye Q (2020) Prototype mixture models for few-shot semantic segmentation. In: Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, 23\u201328 August, 2020, Proceedings, Part VIII 16, pp 763\u2013778 . Springer","DOI":"10.1007\/978-3-030-58598-3_45"},{"key":"5986_CR39","first-page":"823","volume":"35","author":"G Zhang","year":"2022","unstructured":"Zhang G, Navasardyan S, Chen L, Zhao Y, Wei Y, Shi H et al (2022) Mask matching transformer for few-shot segmentation. Adv Neural Inf Process Syst 35:823\u2013836","journal-title":"Adv Neural Inf Process Syst"},{"key":"5986_CR40","doi-asserted-by":"crossref","unstructured":"Xu W, Huang H, Cheng M, Yu L, Wu Q, Zhang J (2023) Masked cross-image encoding for few-shot segmentation. In: 2023 IEEE International Conference on Multimedia and Expo (ICME), pp 744\u2013749. IEEE","DOI":"10.1109\/ICME55011.2023.00133"},{"key":"5986_CR41","doi-asserted-by":"crossref","unstructured":"Liu J, Bao Y, Xie G-S, Xiong H, Sonke J-J, Gavves E (2022) Dynamic prototype convolution network for few-shot semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 11553\u201311562","DOI":"10.1109\/CVPR52688.2022.01126"},{"key":"5986_CR42","doi-asserted-by":"crossref","unstructured":"Peng B, Tian Z, Wu X, Wang C, Liu S, Su J, Jia J (2023) Hierarchical dense correlation distillation for few-shot segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 23641\u201323651","DOI":"10.1109\/CVPR52729.2023.02264"},{"key":"5986_CR43","doi-asserted-by":"crossref","unstructured":"Liu H, Peng P, Chen T, Wang Q, Yao Y, Hua X-S (2023) Fecanet: Boosting few-shot semantic segmentation with feature-enhanced context-aware network. IEEE Trans Multimed","DOI":"10.1109\/TMM.2023.3238521"},{"issue":"4","key":"5986_CR44","first-page":"4650","volume":"45","author":"G Cheng","year":"2022","unstructured":"Cheng G, Lang C, Han J (2022) Holistic prototype activation for few-shot segmentation. IEEE Trans Pattern Anal Mach Intell 45(4):4650\u20134666","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"5986_CR45","doi-asserted-by":"crossref","unstructured":"Xu Q, Zhao W, Lin G, Long C (2023) Self-calibrated cross attention network for few-shot segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 655\u2013665","DOI":"10.1109\/ICCV51070.2023.00067"},{"key":"5986_CR46","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham M, Van Gool L, Williams CK, Winn J, Zisserman A (2010) The pascal visual object classes (voc) challenge. Int J Comput Vis 88:303\u2013338","journal-title":"Int J Comput Vis"},{"key":"5986_CR47","doi-asserted-by":"crossref","unstructured":"Hariharan B, Arbel\u00e1ez P, Girshick R, Malik J (2014) Simultaneous detection and segmentation. In: Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, 6-12 September, 2014, Proceedings, Part VII 13, pp 297\u2013312 . Springer","DOI":"10.1007\/978-3-319-10584-0_20"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-024-05986-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-024-05986-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-024-05986-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T15:04:28Z","timestamp":1737385468000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-024-05986-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,10]]},"references-count":47,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["5986"],"URL":"https:\/\/doi.org\/10.1007\/s10489-024-05986-x","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,10]]},"assertion":[{"value":"30 September 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 December 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflicts of interest or competing interests relevant to the content of this manuscript.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest\/Competing Interests"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics Approval and Consent to Participate"}},{"value":"Consent for publication was obtained from all individuals included in this study.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for Publication"}}],"article-number":"119"}}